Comparison between different selection methods of rubber trees

Verardi, Cecília Khusala; Oliveira, André Luís Bombonato de; Silva, Guilherme Augusto Peres; Gouvêa, Lígia Regina Lima; Gonçalves, Paulo de Souza

doi:10.1016/j.indcrop.2013.10.038

Cited by 8 publications

(6 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Regarding the selection methods in statistical genetics, some methodology categories are significant and have been widely used. They include the selection index (Verardi, Oliveira, Silva, Gouvêa, & Gonçalves, 2014), the combined selection method (Ribeiro, Mambrin, Storck, Prigol, & Nogueira, 2013;Verardi et al, 2014), and the REML/BLUP (Restricted Maximum Likelihood/Best Linear Unbiased Prediction) method (Ferreira, Viana, Barroso, Resende, & Amaral Júnior, 2012). However, a new paradigm can be employed in genetic breeding for selection purposes which does not involve stochastic modeling.…”

Section: Discussionmentioning

confidence: 99%

Predicting breeding value of body weight at 6-month age using Artificial Neural Networks in Kermani sheep breed

Ghotbaldini

Mohammadabadi

Nezamabadi‐pour

et al. 2019

Acta Sci. Anim. Sci.

View full text Add to dashboard Cite

The present study aimed to apply artificial neural networks to predict the breeding values of body weight in 6-month age of Kermani sheep. For this purpose, records of 867 lambs including lamb sex, dam age, birth weight, weaning weight, age at 3-month (3 months old), age at 6-month (6 months old) and body weight at 3 months of age were used. Firstly, genetic parameters of the animals were estimated using ASReml software. The data was then pre-processed for using in MATLAB software. After initial experiments on the appropriate neural network architecture for body weight at 6-month age, two networks were examined. A feed-forward back propagation multilayer perceptron (MLP) algorithm was used and 70% of all data used as training data, 15% as testing data and 15% as validating data, to prevent over-fitting of the artificial neural network. Results showed that the both networks capable to predict breeding values for body weight at 6 month-age in Kermani sheep. It can be concluded that artificial neural network has a good ability to predict growth traits in Kermani sheep with an acceptable speed and accuracy. Therefore, this network, instead of commonly-used procedures can be used to estimate the breeding values for productive and reproductive traits in domestic animals.

show abstract

Section: Discussionmentioning

confidence: 99%

Predicting breeding value of body weight at 6-month age using Artificial Neural Networks in Kermani sheep breed

Ghotbaldini

Mohammadabadi

Nezamabadi‐pour

et al. 2019

Acta Sci. Anim. Sci.

View full text Add to dashboard Cite

show abstract

“…There are studies that show that vigor (measured by stem perimeter) is considered the most important character to determine the precocity of the clone, allowing the rubber tree producer to have a faster return of its investment, with greater production in the first years of life, which confirm the efficiency of the early tests (Alem et al, 2015). Based on the high correlation between annual perimeter growth and rubber production and observed results, it is possible to predict that selection with this population is possible in young plants with maximum gain and in short time, minimizing the rubber production cycle (Gonçalves et al, 2006;Verardi et al, 2014). Thus, these two characters were chosen for the use of selection strategies employing the Multi-Effects Index (MEI).…”

Section: Prediction Of Selection Gainsmentioning

confidence: 62%

“…ns not significant. Verardi et al, 2014). The values of the coefficient of relative variation (CV r ) were higher than 0,45 for all the characters that were evaluated in PS and for the characters DMC, P50, PAP e PBS, para a PM.…”

Section: Estimates Of Genetic Parametersmentioning

confidence: 83%

“…In this method, selection is based on genetic measures (net genetic value) and non-phenotypic measures of the candidates for selection (Resende and Higa, 1994). Several studies have been carried out using the MEI method, due to the more expressive gains in selection (Costa et al, 2000a(Costa et al, , 2000bSantos et al, 2016;Arantes et al, 2010;Tung et al, 2010;Silva et al, 2011;Verardi et al, 2013Verardi et al, , 2014Kubota et al, 2015).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Selection strategies for growth characters and rubber yield in two populations of rubber trees in Brazil

Dourado

Moraes

Alves

et al. 2018

Industrial Crops and Products

View full text Add to dashboard Cite

The objective of this work was to evaluate the genetic parameters and estimate genetic gains in two populations of Hevea brasiliensis. The first population of the study is originated from the primary forest of Rio Branco-Acre (wild population-PS), and the other population is originated from clonal matrices (improved population-PM). Thirty-seven progenies were evaluated at 23 years for PS. For PM, 31 progenies at eight years of age were evaluated for growth traits and dry rubber yield. Estimates of the genetic parameters were made using the univariate linear mixed-model additive model REML/BLUP and gains in selection by the Multi-Effects Index (MEI) method. The selection strategies of 50%, 40% and 22% of individuals for the character of dry rubber yield (PBS) and stem perimeter (PAP) using the multi-effects index revealed high and low selection gains in both populations. For MP, the strategy of selection between and within progenies was more appropriate and for PS, the individual selection. The gains obtained in the selection were 54% for the PBS character in the improved population of 0.46% for the PAP character for the wild population.

show abstract

“…With regard to the statistical genetic methods for selection, some methodology categories are noteworthy, and have been widely used as follows: selection index (Verardi et al, 2014), the combined selection method (Ribeiro et al, 2013;Verardi et al, 2014) and the REML-BLUP method (Ferreira et al, 2012). Nonetheless, a new paradigm can be employed in genetic breeding for selection purposes that does not involve stochastic modeling, but instead the principles of learning in a computational intelligence approach.…”

Section: Introductionmentioning

confidence: 99%

Neural networks for predicting breeding values and genetic gains

Silva

Tomaz

Sant’Anna

et al. 2014

Sci. agric. (Piracicaba, Braz.)

View full text Add to dashboard Cite

Analysis using Artificial Neural Networks has been described as an approach in the decision-making process that, although incipient, has been reported as presenting high potential for use in animal and plant breeding. In this study, we introduce the procedure of using the expanded data set for training the network. Wealso proposed using statistical parameters to estimate the breeding value of genotypes in simulated scenarios, in addition to the mean phenotypic value in a feed-forward back propagation multilayer perceptron network. After evaluating artificial neural network configurations, our results showed its superiority to estimates based on linear models, as well as its applicability in the genetic value prediction process. The results further indicated the good generalization performance of the neural network model in several additional validation experiments.

show abstract

Comparison between different selection methods of rubber trees

Cited by 8 publications

References 10 publications

Predicting breeding value of body weight at 6-month age using Artificial Neural Networks in Kermani sheep breed

Predicting breeding value of body weight at 6-month age using Artificial Neural Networks in Kermani sheep breed

Selection strategies for growth characters and rubber yield in two populations of rubber trees in Brazil

Neural networks for predicting breeding values and genetic gains

Contact Info

Product

Resources

About